当前位置：文档库 › 人手图片的数据集(Arpit Mittal, Andrew Zisserman and Phil Torr )_计算机图形_科研数据集

人手图片的数据集(Arpit Mittal, Andrew Zisserman and Phil Torr )_计算机图形_科研数据集

人手图片的数据集(Arpit Mittal, Andrew Zisserman and Phil Torr )(hand dataset(Arpit Mittal, Andrew

Zisserman and Phil Torr ))

数据介绍：

We introduce a comprehensive dataset of hand images collected from various different public image data set sources as listed in Table 1. A total of 13050 hand instances are annotated. Hand instances larger than a fixed area of bounding box (1500 sq. pixels) are considered 'big' enough for detections and are used for evaluation. This gives around 4170 high quality hand instances. While collecting the data, no restriction was imposed on the pose or visibility of people, nor was any constraint imposed on the environment. In each image, all the hands that can be perceived clearly by humans are annotated. The annotations consist of a bounding rectangle, which does not have to be axis aligned, oriented with respect to the wrist.

关键词：

手,图像,验证,培训,测试, hand,image,validation,training,test,

数据格式：

IMAGE

数据详细介绍：

H a n d D a t a s e t

Arpit Mittal, Andrew Zisserman and Phil Torr

Overview

Table 1: Statistics of the hand dataset.

* The movie dataset contains frames from the films 'Four weddings and a funeral', 'Apollo 13', 'About a boy' and 'Forrest Gump'. Downloads

Please cite [1] if you use this dataset.

Publications

[1] A. Mittal, A. Zisserman, P. H. S. Torr

Hand detection using multiple proposals

British Machine Vision Conference, 2011

[2] M. J. Jones and J. M. Rehg

Statistical color models with application to skin detection

International Journal of Computer Vision, 2002

Acknowledgements

This work is funded by the ERC grant VisRec no. 228180 and ONR MURI N00014-07-1-0182.

数据预览：

点此下载完整数据集

3D Photography Dataset-Action Figure (Warrior) (3D摄影数据集图(战士))_图像处理_科研数据集

3D Photography Dataset-Action Figure (Warrior) （3D摄影数据集图（战士））英文关键词： multiview stereo data,images,camera parameters,contours, 中文关键词：多视图的立体数据、图像、摄像机参数、轮廓，数据格式： IMAGE 数据介绍： The following are multiview stereo data sets captured in our lab: a set of images, camera parameters and extracted apparent contours of a single rigid object. Each data set consists of 24 images. Image resolutions range from 1400x1300 pixels^2 to 2000x1800 pixels^2 depending on the data set. For calibration, we have used "Camera Calibration Toolbox for Matlab" by Jean-Yves Bouguet to estimate both the intrinsic and the extrinsic camera parameters. All the images have been corrected to remove radial and tangential distortions. For contour extraction, first, Photoshop has been used to segment the foreground from each

图像处理_Holidays Photos Dataset(假日风景图片数据集)

Holidays Photos Dataset(假日风景图片数据集) 数据摘要： The dataset is a set of images which mainly contains the holidays photos. These were taken on purpose to test the robustness to various attacks: rotations, viewpoint and illumination changes, blurring, etc.. 中文关键词：图像,假日图片,稳健性,视角,照明度,分辨率,校正, 英文关键词： image,holidays photos,robustness,viewpoint,illumination,resolution,correction, 数据格式： IMAGE 数据用途：图像变换,图像矫正数据详细介绍： INRIA Holidays dataset

The Holidays dataset is a set of images which mainly contains some of our personal holidays photos. The remaining ones were taken on purpose to test the robustness to various attacks: rotations, viewpoint and illumination changes, blurring, etc. The dataset includes a very large variety of scene types (natural, man-made, water and fire effects, etc) and images are in high resolution. The dataset contains 500 image groups, each of which represents a distinct scene or object. The first image of each group is the query image and the correct retrieval results are the other images of the group. Notes About Files in Dataset Descriptors in the dataset are stored in raw together with the region information provided by the software of Krystian Mikolajczyk. There is no header (use the file length to find the number of descriptors). A descriptor takes 168 bytes (floats and ints take 4 bytes, and are stored in little endian): A matlab file to read .siftgeo files. .fvecs format This one is used to store centroids. As for the .siftgeo format, there is no header. Centroids are stored in raw. Each centroid takes 516 bytes, as shown below.

ImageNet图像数据集处理及说明_20160920

1 ImageNet 图像数据集分类标签及对应的名称这份数据是ILSVRC2012年比赛所有的数据，下载解压后如下：请确认的确是你想要的数据，千万不要出现下载了一个礼拜，解压缩一个礼拜结果发现不是你想要的。 2.下载前请保证硬盘至少要有141G 空间，多多益善。 3.必须使用百度云客户端下载，支持断点续传，不然出了点问题一切白费了。上传时速度1.4M/s 用了大约30个小时完成。 4. 所有图片共分为1000个类别，这1000个类别的分类标签及对应的名称如下所述。例如第1类的标签为n01440764，第1类的名称为'tench, Tinca tinca'； Define a cell of matlab: Label1(1)={'daffff'} Label2{1}=('dddfff') Label2{1}={'dddfff'} >> https://www.wendangku.net/doc/6118747641.html, Columns 1 through 9 'n01440764' 'n01443537' 'n01484850' 'n01491361' 'n01494475' 'n01496331' 'n01498041' 'n01514668' 'n01514859' Columns 10 through 18 'n01518878' 'n01530575' 'n01531178' 'n01532829' 'n01534433' 'n01537544' 'n01558993' 'n01560419' 'n01580077'

Columns 19 through 27 'n01582220' 'n01592084' 'n01601694' 'n01608432' 'n01614925' 'n01616318' 'n01622779' 'n01629819' 'n01630670' Columns 28 through 36 'n01631663' 'n01632458' 'n01632777' 'n01641577' 'n01644373' 'n01644900' 'n01664065' 'n01665541' 'n01667114' Columns 37 through 45 'n01667778' 'n01669191' 'n01675722' 'n01677366' 'n01682714' 'n01685808' 'n01687978' 'n01688243' 'n01689811' Columns 46 through 54 'n01692333' 'n01693334' 'n01694178' 'n01695060' 'n01697457' 'n01698640' 'n01704323' 'n01728572' 'n01728920' Columns 55 through 63 'n01729322' 'n01729977' 'n01734418' 'n01735189' 'n01737021' 'n01739381' 'n01740131' 'n01742172' 'n01744401' Columns 64 through 72 'n01748264' 'n01749939' 'n01751748' 'n01753488' 'n01755581' 'n01756291' 'n01768244' 'n01770081' 'n01770393' Columns 73 through 81 'n01773157' 'n01773549' 'n01773797' 'n01774384' 'n01774750' 'n01775062' 'n01776313' 'n01784675' 'n01795545' Columns 82 through 90 'n01796340' 'n01797886' 'n01798484' 'n01806143' 'n01806567' 'n01807496' 'n01817953' 'n01818515' 'n01819313' Columns 91 through 99 'n01820546' 'n01824575' 'n01828970' 'n01829413' 'n01833805' 'n01843065' 'n01843383' 'n01847000' 'n01855032' Columns 100 through 108 'n01855672' 'n01860187' 'n01871265' 'n01872401' 'n01873310' 'n01877812' 'n01882714' 'n01883070' 'n01910747' 2

2014名师联1800G设计师资料集图片案例方案软装作品

https://www.wendangku.net/doc/6118747641.html,D郑中专题（120G） https://www.wendangku.net/doc/6118747641.html,/cjY34rTaABEAX 访问密码5760 https://www.wendangku.net/doc/6118747641.html,/cjY3iULpqMSjQ 访问密码3bbf https://www.wendangku.net/doc/6118747641.html,/cjY3hbD2Dbudd 访问密码c4b3 https://www.wendangku.net/doc/6118747641.html,/cjY37HsnjTcGv 访问密码4e99 https://www.wendangku.net/doc/6118747641.html,/cjYuALCmunNxp 访问密码cb9b https://www.wendangku.net/doc/6118747641.html,/cjYuKrIzMgvKz 访问密码93df https://www.wendangku.net/doc/6118747641.html,/cjYuZU7rybZXi 访问密码1bba https://www.wendangku.net/doc/6118747641.html,/cjYuQvpM5T96b 访问密码3d9d https://www.wendangku.net/doc/6118747641.html,/cjYumnIeEtGKC 访问密码88b6 https://www.wendangku.net/doc/6118747641.html,/cjYuFh9AE2JW A 访问密码19a9 01CCD--丽江伯尔曼酒店独家资料 https://www.wendangku.net/doc/6118747641.html,/cjYBxqe2sEShK 访问密码908d 2.HBA专题（38G） https://www.wendangku.net/doc/6118747641.html,/cjYuqLhiubMTI 访问密码1a0b https://www.wendangku.net/doc/6118747641.html,/cjYu6nIP3V yuA 访问密码30de https://www.wendangku.net/doc/6118747641.html,/cjYu9f36dXcJy 访问密码8209 https://www.wendangku.net/doc/6118747641.html,/cjYrgnZF2pPba 访问密码e3ad https://www.wendangku.net/doc/6118747641.html,/cjYrj2vmGwZKj 访问密码ec1b HBA－北京某豪宅样板房 https://www.wendangku.net/doc/6118747641.html,/cjYBRjUfYeGh6 访问密码79ea HBA财富公馆施工图 https://www.wendangku.net/doc/6118747641.html,/cjYB6ngjUNsKH 访问密码d024 HBA-东莞[希尔顿酒店]概念设计方案 https://www.wendangku.net/doc/6118747641.html,/cjYBkTNvUKWKu 访问密码3474 3-YABU专题【32G】 https://www.wendangku.net/doc/6118747641.html,/cjYrM96G2wK2b 访问密码eb85 https://www.wendangku.net/doc/6118747641.html,/cjYri2kvIc7FS 访问密码be0a https://www.wendangku.net/doc/6118747641.html,/cjYrTpVW A2hfC 访问密码a636 https://www.wendangku.net/doc/6118747641.html,/cjYraaw9gDNER 访问密码44ce YABU作品集 https://www.wendangku.net/doc/6118747641.html,/cjYBTg7UW7h4v 访问密码0d19 https://www.wendangku.net/doc/6118747641.html,/cjYBhHEpzGBU6 访问密码c617 yabu雅布室内设计作品集及设计元素分

CVC虚拟行人数据集(CVC Virtual Pedestrian Dataset)_计算机图形_科研数据集

CVC虚拟行人数据集(CVC Virtual Pedestrian Dataset) 数据介绍： This is the virtual pedestrian dataset, generated using Half-Life 2 graphics engine. The dataset consists of 1678 virtual pedestrians (with their corresponding horizontal mirrors) and 2048 pedestrian-free background images to extract negatives for training. 关键词： CVC,虚拟,行人,Half-Life 2图形引擎, CVC,Virtual,Pedestrian,Half-Life 2 graphics engine, 数据格式： IMAGE 数据详细介绍： CVC Virtual Pedestrian Dataset This is the virtual pedestrian dataset, generated using Half-Life 2 graphics engine. The dataset consists of 1678 virtual pedestrians (with their corresponding horizontal mirrors) and 2048 pedestrian-free background images to extract negatives for training. Here are some examples of the database:

图像处理_Semeion Handwritten Digit Data Set(Semeion手写体数字数据集)

Semeion Handwritten Digit Data Set(Semeion手写体数字数据集) 数据摘要： 1593 handwritten digits from around 80 persons were scanned, stretched in a rectangular box 16x16 in a gray scale of 256 values.Then each pixel of each image was scaled into a bolean (1/0) value using a fixed threshold. Each person wrote on a paper all the digits from 0 to 9, twice. The commitment was to write the digit the first time in the normal way (trying to write each digit accurately) and the second time in a fast way (with no accuracy). The best validation protocol for this dataset seems to be a 5x2CV, 50% Tune (Train +Test) and completly blind 50% Validation 中文关键词： Semeion,手写数字,数据集,0到9,

英文关键词： Semeion,Handwritten Digit,Data Set,0 to 9, 数据格式： TEXT 数据用途： Classification 数据详细介绍： Semeion Handwritten Digit Data Set Abstract: 1593 handwritten digits from around 80 persons were scanned, stretched in a rectangular box 16x16 in a gray scale of 256 values. Source: The dataset was created by Tactile Srl, Brescia, Italy (http://www.tattile.it) and donated in 1994 to Semeion Research Center of Sciences of Communication, Rome, Italy (http://www.semeion.it), for machine learning research.

机器学习_Statlog (Image Segmentation) Data Set(Statlog(图像分割)数据集)

Statlog (Image Segmentation) Data Set(Statlog(图像分割)数据集) 数据摘要： This dataset is an image segmentation database similar to a database already present in the repository (Image segmentation database) but in a slightly different form. 中文关键词： Statlog,图像分割,多变量,分类,UCI, 英文关键词： Statlog,Image Segmentation,Multivariate,Classification,UCI, 数据格式： TEXT 数据用途： This data is used for classifacation. 数据详细介绍： Statlog (Image Segmentation) Data Set

Abstract: This dataset is an image segmentation database similar to a database already Source: Creators: Vision Group, University of Massachusetts Donor: Vision Group (Carla Brodley, brodley '@' https://www.wendangku.net/doc/6118747641.html,) Data Set Information: The instances were drawn randomly from a database of 7 outdoor images. The images were handsegmented to create a classification for every pixel. Each instance is a 3x3 region. Attribute Information: 1. region-centroid-col: the column of the center pixel of the region. 2. region-centroid-row: the row of the center pixel of the region. 3. region-pixel-count: the number of pixels in a region = 9. 4. short-line-density-5: the results of a line extractoin algorithm that counts how many lines of length 5 (any orientation) with low contrast, less than or equal to 5, go through the region. 5. short-line-density-2: same as short-line-density-5 but counts lines of high contrast, greater than 5. 6. vedge-mean: measure the contrast of horizontally adjacent pixels in the region. There are 6, the mean and standard deviation are given. This attribute is used as a vertical edge detector. 7. vegde-sd: (see 6) 8. hedge-mean: measures the contrast of vertically adjacent pixels. Used for horizontal line detection. 9. hedge-sd: (see 8). 10. intensity-mean: the average over the region of (R + G + B)/3 11. rawred-mean: the average over the region of the R value.

图像处理_CMU SRI Motion Image Dataset(CMU SRI运动图像数据集)

CMU SRI Motion Image Dataset(CMU SRI运动图像数据集) 数据摘要： Taken with the Sony camera (borrowed from Stan Reifel) with the 12.5mm lens and the IR filter from the Fairchild head (which Bill took out for other reasons). The Sony camera has several advantages over the GE and the Fairchild. 中文关键词：图像,索尼相机,通用电气,灵敏度,镜头, 英文关键词： image,Sony camera,GE,sensitivity,lens, 数据格式： IMAGE 数据用途：图像处理，摄影技术数据详细介绍：

SRI Motion Image Dataset Taken with the Sony camera (borrowed from Stan Reifel) with the 12.5mm lens and the IR filter from the Fairchild head (which Bill took out for other reasons). The Sony camera has several advantages over the GE and the Fairchild. It is inexpensive ($1000.). It appears to have none of the patterning I've seen in both the others (4 row and 4 column-type of "mesh" over the image). It has much better sensitivity than the Fairchild (I could barely see anything with the same lens and filter on the Fairchild.) It appears to have good blooming characteristics. The sunlight and flourescents don't cause it to bloom like the Fairchild. I took CAL0.IMG and CAL20.IMG via USR:[BOLLES]CALCAM.ICP, which takes one picture, moves the table 20" back from the target, and takes the second one. Using the formula of March 28 (page 3) I computed the following pixel sizes: 1 horizontal pixel = .001170018" 1 vertical pixel = .001089928" which would make the 256x240 (sampled down from 512x480) image plane to be .2995"(h) x .2616"(v). The specs say that the sensitive area on the chip is 8.8mm x 6.6mm or .3477" x .2596". I don't understand the difference in the horizontal sizes. Using this formula the two image plane distances corresponding to 30" on the target were .1602925" and .1689388", which I believe should be the same, if the optics is symmetric, which it is. I don't know why there is such a difference. (Maybe poor pointing accuracy of the cursor on the images ... only to the closest pixel.) I then used the 90" tape measured distance from the lens center to the target to get another estimate of the image plane distances. For a 30" target, the image plane distance should be 1/3 of F, which is .492126, which is .164042". Since that is a compromise between the two estimates from the first method I decided to use it and recompute the pixel sizes. The new sizes are: 1 horizontal pixel = .001197387" 1 vertical pixel = .001058336"

机器学习_CMU Face Images Data Set(CMU人脸图像数据集)

CMU Face Images Data Set(CMU人脸图像数据集) 数据摘要： This data consists of 640 black and white face images of people taken with varying pose (straight, left, right, up), expression (neutral, happy, sad, angry), eyes (wearing sunglasses or not), and size 中文关键词：人脸,图像,分类,UCI, 英文关键词： Faces,Image,Classification,UCI, 数据格式： TEXT 数据用途： This data set is used for classification. 数据详细介绍： CMU Face Images Data Set

Abstract: This data consists of 640 black and white face images of people taken with varying pose (straight, left, right, up), expression (neutral, happy, sad, angry), eyes (wearing sunglasses or not), and size Source: Original Owner and Donor: Tom Mitchell School of Computer Science Carnegie Mellon University tom.mitchell '@' https://www.wendangku.net/doc/6118747641.html, https://www.wendangku.net/doc/6118747641.html,/~tom/ Data Set Information: Each image can be characterized by the pose, expression, eyes, and size. There are 32 images for each person capturing every combination of features. To view the images, you can use the program xv. The image data can be found in /faces. This directory contains 20 subdirectories, one for each person, named by userid. Each of these directories contains several different face images of the same person. You will be interested in the images with the following naming convention: .pgm is the user id of the person in the image, and this field has 20 values: an2i, at33, boland, bpm, ch4f, cheyer, choon, danieln, glickman, karyadi, kawamura, kk49, megak, mitchell, night, phoebe, saavik, steffi, sz24, and tammo. is the head position of the person, and this field has 4 values: straight, left, right, up. is the facial expression of the person, and this field has 4 values:

人手图片的数据集(Arpit Mittal, Andrew Zisserman and Phil Torr )_计算机图形_科研数据集

人手图片的数据集(Arpit Mittal, Andrew Zisserman and Phil Torr )(hand dataset(Arpit Mittal, Andrew Zisserman and Phil Torr )) 数据介绍： We introduce a comprehensive dataset of hand images collected from various different public image data set sources as listed in Table 1. A total of 13050 hand instances are annotated. Hand instances larger than a fixed area of bounding box (1500 sq. pixels) are considered 'big' enough for detections and are used for evaluation. This gives around 4170 high quality hand instances. While collecting the data, no restriction was imposed on the pose or visibility of people, nor was any constraint imposed on the environment. In each image, all the hands that can be perceived clearly by humans are annotated. The annotations consist of a bounding rectangle, which does not have to be axis aligned, oriented with respect to the wrist. 关键词：手,图像,验证,培训,测试, hand,image,validation,training,test, 数据格式： IMAGE

关于建立集团信息图片资料库的方案

关于建立集团信息图片资料库的方案为有效整合资源，提升信息化管理水平，优化信息资源利用水平，进一步加强集团文字和图片资料的收集与管理，充分发挥各类信息资料对集团及子公司各项工作的支持、宣传、见证和数据保障作用，需建立集团信息图片资料库，企划部特制定本实施方案。一、目的意义集团信息图片资料库的建立，能改善集团信息图片资源不完善的局面，为集团、各子公司和社会各界提供丰富的信息资源。建立集团信息图片资料库的一个重要目标是，资料库所拥有的信息资源能够实现集团高度的共享，促进信息流通利用和平等共享。二、信息图片库重点内容信息图片资料库的建设，包括对文字图片资料的收集（获得及验证）、整理（以系统的或有条理的方法）、维持（存储并不断更新）和显示（可用电子的或其他的方法单独得到）。信息图片资料库的建立需紧紧围绕全集团工作，为集团

及子公司服务，信息图片资料库收录内容应突出发展中的重点、热点、难点问题，广泛收集，深度挖掘，重点反映，紧密结合实际，突出重点，不断在文字图片库服务的针对性上下功夫，坚持以质量为中心，有计划、有针对性的搞好各类文字图片资料的加工和综合利用。建立信息图片资料库后，需整理入库的重点内容分类如下： 1．集团及各子公司重大会议、重大事件、重大活动等相关文字及图片资料； 2．集团大事记、发展规划、战略合作、重点项目等文字及图片资料； 3．集团社会责任、家乡建设、贫困助学、老年基金、公益赞助等相关文字图片资料； 4．新闻媒体对集团及子公司各类报道的文字图片资料； 5、三亚市委、市政府各项会议的信息简报。三、相关要求和职责分工一是规范入库内容。资料库由文字资料库和图片资料库构成，要求信息图片资料能够全面反映和重点体现相结合的原则，入库的文字图片资料既能反映事件发展的整个过程，又能突出事件的主题和重点。信息图片资料库的规模应与集

面部图像数据集：Faces96(Collection of Facial Images Faces96)_图像处理_科研数据集

面部图像数据集：Faces96(Collection of Facial Images: Faces96) 数据介绍： Using a fixed camera, a sequence of 20 images per individual was taken. During the sequence the subject takes one step forward towards the camera. This movement is used to introduce significant head variations between images of same individual. 关键词：比较,生物识别,处理,汇总,图片, comparative,Biometric,processing,summary,Images, 数据格式： IMAGE 数据详细介绍： Collection of Facial Images: Faces96 -------------------------------------------------------------------------------- Acquisition conditions Using a fixed camera, a sequence of 20 images per individual was taken. During the sequence the subject takes one step forward towards the camera. This movement is used to introduce significant head variations

CBSR近红外人脸数据集(CBSR NIR Face Dataset)_图像处理_科研数据集

CBSR近红外人脸数据集(CBSR NIR Face Dataset) 数据介绍： NIR face detection, NIR eye detection, NIR face recognition 关键词： CBSR,近红外,眼睛检测,人脸检测,人脸识别, CBSR,NIR,eye detection,face detection,face recognition, 数据格式： IMAGE 数据详细介绍： CBSR NIR Face Dataset Topic of Interest: NIR face detection, NIR eye detection, NIR face recognition Sensor Details: The images were taken by an NIR camera with active NIR lighting. More details are available in reference below.

Data Details: 3,940 NIR face images of 197 people. The image size is 480 by 640 pixels, 8 bit, without compression. Images are divided into a gallery set and a probe set. In the gallery set, there are 8 images per person. In the probe set, 12 images per person. The image information is provided, which gives the image number, person number, and eye coordinates. Requested Citation Acknowledgment: IEEE OTCBVS WS Series Bench; Center for Biometrics and Security Research (CBSR) https://www.wendangku.net/doc/6118747641.html,; AuthenMetric Co. Ltd (Beijing) https://www.wendangku.net/doc/6118747641.html, Also see: Stan Z. Li, RuFeng Chu, ShengCai Liao, Lun Zhang, "Illumination Invariant Face Recognition Using Near-infrared Images," IEEE Transactions on Pattern Analysis and Machine Intelligence (Special issue on Biometrics: Progress and Directions), Vol.29, No.4, April 2007, pp. 627-639. [pdf] Point-of-contact: Stan Z. Li, szli[at]https://www.wendangku.net/doc/6118747641.html,, szli[at]https://www.wendangku.net/doc/6118747641.html, Download: Click here to download this dataset. [NIR_face_dataset.zip] (NIR face dataset) [gallery-groundtruth.txt] (gallery ground truth) [probe-groundtruth.txt] (probe ground truth) Dataset includes 3,940 NIR face images of 197 persons. The image size is 480 by 640 pixels, 8 bit, without compression. The 3,940 images are divided into a gallery set and a probe set. In the gallery set, there are 8 images per person. In the probe set, 12 images per person.

图像数据格式基础知识.doc

所谓位映像，即是指一个二维的像素矩阵，而位图就是采用位映像方法显示和存储图像。一幅图像的显示就是将图像的像素映射到屏幕的像素上并显示一定的颜色。当一幅图形的像素由彩色表示时就是我们通常所说的彩色图像了。由于数字图像可以表示为矩阵的形式，所以在计算机数字图像处理程序中，通常用二维数组来存放图像数据。二维数组的行对应图像的高，二维数组的列对应图像的宽，二维数组的元素对应图像的像素，二维数组元素的值就是像素的灰度值。采用二维数组来存储数字图像，符合二维图像的行列特性，同时也便于程序的寻址操作，使得计算机图像编程十分方便。图像的问题数据是一个二维数组（矩阵），矩阵的每一个元素对应了图像的一个像素, 当保存一幅图像时，不但要保存图像的位图数据矩阵，还要将每个像素的颜色保存下来，颜色的记录是利用颜色表来完成的。颜色表，也叫颜色查找表，是图像像素数据的颜色索引表。对于真彩色图像，每个像素占存储空间3个字节（24位），分别对应R, G, B三个分量, 每个像素的值己经将该像素的颜色记录下来了，不再需要颜色表，因此24位真彩色位图没有颜色表。彩色图像可以由RGB彩色空间表示。彩色空间是用来表示彩色的数学模型，又被称为彩色模型。计算计算上显示的图像经常有二值图像、灰度图像、伪彩色图像及真彩色图像等不同格式类型。而灰度和彩色格式是数字图像处理中最常用到的类型。灰度图像是数字图像的最基本形式，灰度图像可以由黑白照片数字化得到，或从彩色图像进行去色处理得到。灰度图像只表达图像的亮度信息而没有彩色信息，因此，灰度图像的每个像素点上只包含一个量化的灰度级（即灰度值），用来表示该点的亮度水平，并且通常用1个字节（8个二进制位）来存储灰度值。彩色图像数据不仅包含亮度信息，还包含颜色信息。 BMP文件结构及其存取：数字图像在外存储器设备中的存储形式是图像文件，图像必须按照某个已知的、公认的数据存储顺序和结构进行存储，才能使不同的程序对图像文件顺利进行打开或存盘操作, 实现数据共享。图像数据了啊文件中的存储顺序和结构称为图像文件格式。目前广为流传的图像文件格式有许多种，常见的格式包括BMP, GIF, JPEG, TIFF, PSD, DICOM, MPEG等。在各种图像文件格式中，一部分时由某个软硬件厂商提出并广泛接受和采用的格式，如BMP, GIF和PSD格式。另一部分是由各神国际标准组织提出的形式，例如JPEG/TIFF和DICOM,其中JEPG是国际静止图像压缩标准组织提出的格式，TIFF是由部分厂商组织提出的格式，DICOM是医学图像国际标准组织提取的医学图像专用格式。 BMP文件是Windows操作系统所推荐和支持的图像文件格式，是一?种将内存或显示器的图像数据不经过压缩而直接按位存盘的文件格式，所以称为位图（bitmap）文件，因其文件扩展名为BMP,故称为BMP文件格式，简称BMP文件。 BMP文件结构： BMP文件图像被分成4部分：位图文件头、位图信息头、颜色表和位图数据。